Skip to main content
Glama
shubhamshnd

ytmcp

by shubhamshnd
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

YTMcp - YouTube Transcript MCP Server

PyPI version Python Support License: MIT

A Model Context Protocol (MCP) server that enables AI assistants like Claude to fetch YouTube video transcripts with precise timestamps. Built on top of the excellent youtube-transcript-api by @jdepoix.

🎯 Features

  • 🎥 Fetch YouTube transcripts with start/end timestamps

  • 🌍 Multi-language support with automatic fallback

  • ⏱️ Time-range filtering for specific video segments

  • 📋 List available languages for any video

  • 🔍 Smart URL parsing - works with any YouTube URL format

  • 🤖 MCP compatible - works with Claude Desktop and other MCP clients

  • 🚀 Zero external dependencies - bundled with transcript API

  • 🛡️ Comprehensive error handling for robust operation

Related MCP server: YouTube Transcript MCP Server

📦 Installation

pip install ytmcp

🚀 Quick Start

1. Run as MCP Server

ytmcp

The server will start and listen for MCP requests via stdio.

2. Configure with Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "ytmcp"
    }
  }
}

3. Test Installation

# Test the server functionality
ytmcp --test

# Test with a specific video
ytmcp --test --video-id dQw4w9WgXcQ

# Check version
ytmcp --version

4. Use with Claude

Once configured, you can ask Claude natural language questions like:

  • "Get the transcript for this YouTube video: https://www.youtube.com/watch?v=dQw4w9WgXcQ"

  • "What transcript languages are available for this video?"

  • "Get me the transcript from 2:30 to 5:00 in this video"

  • "Summarize the key points from this YouTube video's transcript"

🛠️ Available Tools

get_transcript

Fetch complete video transcript with timestamps.

Parameters:

  • video_url_or_id (required): YouTube URL or video ID

  • languages (optional): Array of language codes in priority order (default: ["en"])

  • preserve_formatting (optional): Keep HTML formatting (default: false)

  • include_timestamps (optional): Include start/end times (default: true)

Example Usage:

{
  "name": "get_transcript",
  "arguments": {
    "video_url_or_id": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
    "languages": ["en", "es"],
    "include_timestamps": true
  }
}

Example Response:

{
  "video_id": "dQw4w9WgXcQ",
  "language": "English",
  "language_code": "en",
  "is_generated": true,
  "transcript_count": 142,
  "transcript": [
    {
      "text": "We're no strangers to love",
      "start": 15.5,
      "duration": 2.3,
      "end": 17.8
    },
    {
      "text": "You know the rules and so do I",
      "start": 17.8,
      "duration": 2.1,
      "end": 19.9
    }
  ]
}

list_available_transcripts

List all available transcript languages for a video.

Parameters:

  • video_url_or_id (required): YouTube URL or video ID

Example Usage:

{
  "name": "list_available_transcripts",
  "arguments": {
    "video_url_or_id": "dQw4w9WgXcQ"
  }
}

Example Response:

{
  "video_id": "dQw4w9WgXcQ",
  "manually_created_transcripts": [
    {
      "language": "English",
      "language_code": "en",
      "is_translatable": true
    }
  ],
  "auto_generated_transcripts": [
    {
      "language": "English (auto-generated)",
      "language_code": "en",
      "is_translatable": true
    }
  ],
  "total_transcripts": 2
}

get_transcript_with_time_range

Get transcript for specific time range.

Parameters:

  • video_url_or_id (required): YouTube URL or video ID

  • start_time (required): Start time in seconds

  • end_time (required): End time in seconds

  • languages (optional): Language preferences (default: ["en"])

  • preserve_formatting (optional): Keep HTML formatting (default: false)

Example Usage:

{
  "name": "get_transcript_with_time_range",
  "arguments": {
    "video_url_or_id": "dQw4w9WgXcQ",
    "start_time": 30.0,
    "end_time": 90.0,
    "languages": ["en"]
  }
}

Example Response:

{
  "video_id": "dQw4w9WgXcQ",
  "language": "English",
  "language_code": "en",
  "is_generated": true,
  "time_range": {
    "start": 30.0,
    "end": 90.0
  },
  "filtered_transcript": [
    {
      "text": "Never gonna give you up",
      "start": 32.1,
      "duration": 1.8,
      "end": 33.9
    }
  ],
  "snippet_count": 15
}

🔧 Configuration Options

Language Codes

YTMcp supports all language codes that YouTube provides. Common ones include:

  • en - English

  • es - Spanish

  • fr - French

  • de - German

  • it - Italian

  • pt - Portuguese

  • ru - Russian

  • ja - Japanese

  • ko - Korean

  • zh - Chinese

URL Format Support

YTMcp automatically extracts video IDs from various YouTube URL formats:

  • https://www.youtube.com/watch?v=VIDEO_ID

  • https://youtu.be/VIDEO_ID

  • https://www.youtube.com/embed/VIDEO_ID

  • https://www.youtube.com/watch?v=VIDEO_ID&t=120s

  • Or just the video ID directly: VIDEO_ID

⚠️ Error Handling

YTMcp provides comprehensive error handling for various scenarios:

Common Error Types

  • Invalid Video ID: Invalid URL or video ID format

  • No Transcript Found: No transcripts available in requested languages

  • Transcripts Disabled: Video has disabled subtitles/captions

  • Video Unavailable: Video is private, deleted, or restricted

  • Request Blocked: IP blocked by YouTube (consider using proxies)

  • Age Restricted: Video requires authentication

Error Response Format

{
  "content": [
    {
      "type": "text",
      "text": "Error: No transcript found for languages: ['de']"
    }
  ]
}

🔄 Advanced Usage

Running as Python Module

python -m ytmcp

Development Mode

# Install in development mode
pip install -e .

# Run tests
ytmcp --test

# Test with verbose output
ytmcp --test --video-id dQw4w9WgXcQ

Proxy Support

If you encounter IP blocking issues, you can extend the server by modifying the YouTube API configuration to use proxies. See the youtube-transcript-api documentation for proxy configuration options.

📚 Use Cases

Content Analysis

  • Video Summarization: Extract transcripts for AI-powered summaries

  • Content Research: Analyze video content programmatically

  • Educational Tools: Create study materials from lecture videos

Accessibility

  • Transcript Generation: Provide text alternatives for video content

  • Translation: Use with translation APIs for multilingual access

  • Search & Discovery: Make video content searchable

Development

  • API Integration: Embed transcript functionality in applications

  • Data Pipeline: Process video transcripts in bulk

  • AI Training: Use transcripts as training data

🐛 Troubleshooting

Installation Issues

# If you get import errors
pip install --upgrade ytmcp

# If command not found
pip install --force-reinstall ytmcp

# Check installation
ytmcp --version

Common Problems

1. Video Not Found

  • Verify the video ID/URL is correct

  • Check if the video is public and available

  • Ensure the video has captions enabled

2. Language Not Available

  • Use list_available_transcripts to see available languages

  • Try fallback languages like ["en", "auto"]

  • Some videos only have auto-generated transcripts

3. Rate Limiting

  • YouTube may temporarily block requests from your IP

  • Consider using proxy configuration for high-volume usage

  • Space out your requests to avoid hitting rate limits

4. Permission Errors

  • Check file permissions if running on Unix systems

  • Ensure Python has permission to execute the script

  • Try running with appropriate user privileges

🤝 Contributing

We welcome contributions! Here's how you can help:

Development Setup

git clone https://github.com/shubhamshnd/ytmcp.git
cd ytmcp
pip install -e ".[dev]"

Running Tests

pytest tests/

Code Style

black ytmcp/
flake8 ytmcp/
mypy ytmcp/

Submitting Changes

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Add tests if applicable

  5. Submit a pull request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Credits

This project is built on top of the excellent youtube-transcript-api by @jdepoix. All core transcript fetching functionality is provided by this library.

Key Dependencies:

🔗 Related Projects

📞 Support

🚀 Roadmap

  • Translation Support: Automatic transcript translation

  • Batch Processing: Handle multiple videos simultaneously

  • Caching: Cache transcripts for improved performance

  • WebSocket Support: Real-time transcript streaming

  • Export Formats: SRT, VTT, and other subtitle formats

  • Search: Full-text search within transcripts

  • Webhooks: Notification system for transcript updates

Made with ❤️ for the MCP and AI community

If you find this project useful, please consider giving it a ⭐ on GitHub!

Available Tools

3 tools
get_transcriptC

Fetch transcript for a YouTube video with timestamps

ParametersJSON Schema
NameRequiredDescriptionDefault
languagesNoPreferred languages in priority order (e.g., ['en', 'es'])
video_url_or_idYesYouTube video URL or video ID
include_timestampsNoWhether to include start and end timestamps
preserve_formattingNoWhether to preserve HTML formatting in transcript text

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It merely restates that timestamps are included, which is already implied by the schema's default. It does not disclose return format, error behavior (e.g., when no transcript is available), or any side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It is concise and to the point. Given the simplicity of the sentence, it earns a high score for structure, though it could be slightly more informative without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 4 parameters, no output schema, and no annotations. The description fails to explain what the returned transcript looks like, how languages are handled, or how this tool relates to the time-range variant. It is incomplete for a tool of this complexity, as the agent would need additional information to invoke it correctly and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond the schema; the mention of timestamps corresponds to the include_timestamps parameter default but offers no extra insight into parameter usage or edge cases.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (fetch) and resource (YouTube video transcript), and mentions 'with timestamps' which hints at a key feature. However, it does not explicitly distinguish this tool from the sibling get_transcript_with_time_range, which could cause confusion about when to use which.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidance is provided. The description does not indicate when to use this tool versus the siblings (list_available_transcripts, get_transcript_with_time_range), nor does it mention any prerequisites or exclusions. Users are left to infer the appropriate use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_transcript_with_time_rangeA

Fetch transcript for a specific time range of a YouTube video

ParametersJSON Schema
NameRequiredDescriptionDefault
end_timeYesEnd time in seconds
languagesNoPreferred languages in priority order
start_timeYesStart time in seconds
video_url_or_idYesYouTube video URL or video ID
preserve_formattingNoWhether to preserve HTML formatting

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. The verb 'Fetch' implies a read-only operation, but the description does not disclose error behavior, language fallback behavior, or what happens if no transcript exists for the range. It provides minimal behavioral context beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It is highly concise and appropriate for the tool's simplicity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description should clarify what the tool returns to some degree. It says 'Fetch transcript' but does not indicate return format (e.g., text, JSON, list of segments) or edge-case behavior. Given the simple read-only nature, the description is minimally adequate but leaves gaps in context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% parameter description coverage, so the baseline is 3. The description does not add any parameter-specific meaning beyond what the schema already provides; it merely contextualizes the time-range parameters generically.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches a transcript for a specific time range of a YouTube video, using a specific verb ('Fetch') and resource ('transcript for a specific time range'). This distinguishes it from sibling tools that list available transcripts or fetch full transcripts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates the use case (fetching a transcript segment by time range), which provides clear context. However, it does not explicitly name alternatives or state when not to use this tool, so it lacks explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_available_transcriptsA

List all available transcript languages for a YouTube video

ParametersJSON Schema
NameRequiredDescriptionDefault
video_url_or_idYesYouTube video URL or video ID

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of disclosing behavior. It clearly indicates a read-only listing operation, but adds no additional details such as return format, behavior when no transcripts exist, or whether auto-generated captions are included. This is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no unnecessary words or repetition. It is front-loaded with the action and resource, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema, no complex nested objects), the description is sufficient for an agent to understand the tool's core function. It lacks some behavioral details like output shape, but for a listing operation this is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with the parameter description 'YouTube video URL or video ID'. The tool description does not add any extra meaning beyond the schema, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'list' and clearly identifies the resource ('available transcript languages for a YouTube video'). It distinguishes itself from sibling tools (get_transcript, get_transcript_with_time_range) by focusing on listing languages rather than fetching transcript content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage context is implied: one would call this tool to discover which transcript languages are available before fetching a transcript. However, it does not explicitly mention when to use it over the sibling tools or provide any exclusion criteria, leaving the guidance implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0
Disambiguation4/5

The tools are mostly distinct: listing available transcripts and fetching a full transcript are clearly different. However, get_transcript and get_transcript_with_time_range both fetch transcripts and could be confused, though the time-range description mitigates ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using 'get_' and 'list_', with descriptive modifiers like 'with_time_range'. The naming is predictable and clearly maps to each tool's purpose.

Tool Count5/5

With only 3 tools, the server is tightly scoped to YouTube transcript retrieval. This is an appropriate size for such a niche domain, with no unnecessary bloat.

Completeness3/5

The set covers listing languages and fetching transcripts (full and by range), but there is no explicit way to choose a specific language from the list. This creates a potential dead end where users can see available languages but not act on them.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/shubhamshnd/ytmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server